论文标题
通过神经消息传递的多对象跟踪和分割
Multi-Object Tracking and Segmentation via Neural Message Passing
论文作者
论文摘要
图提供了一种自然的方式来制定多个对象跟踪（MOT）和多个对象跟踪和分割（MOTS）在逐个检测范式中。但是，他们还引入了学习方法的主要挑战，因为定义一个可以在这种结构化领域运行的模型并不微不足道。在这项工作中，我们利用MOT的经典网络流程公式来定义基于消息传递网络（MPN）的完全可区分的框架。通过直接在图形域上操作，我们的方法可以在整个检测和利用上下文特征上全球推理。然后，它共同预测了数据关联问题的最终解决方案和场景中所有对象的分割掩码，同时利用这两个任务之间的协同作用。我们在几个公开可用的数据集中取得了最新的跟踪和细分结果。我们的代码可在github.com/ocetintas/mpntrackseg上找到。
Graphs offer a natural way to formulate Multiple Object Tracking (MOT) and Multiple Object Tracking and Segmentation (MOTS) within the tracking-by-detection paradigm. However, they also introduce a major challenge for learning methods, as defining a model that can operate on such structured domain is not trivial. In this work, we exploit the classical network flow formulation of MOT to define a fully differentiable framework based on Message Passing Networks (MPNs). By operating directly on the graph domain, our method can reason globally over an entire set of detections and exploit contextual features. It then jointly predicts both final solutions for the data association problem and segmentation masks for all objects in the scene while exploiting synergies between the two tasks. We achieve state-of-the-art results for both tracking and segmentation in several publicly available datasets. Our code is available at github.com/ocetintas/MPNTrackSeg.
